Orientation truncated centre learning for deep face recognition

Secure Learning using Face Recognition has gained significant attention due to its potential solution in curbing and elimination of electronic examination impersonation through enrollment, authentication and authorization. Despite the advancements, existing system often focuses on individual entities, void of models and special dataset to enhance security measure in comprehensively curbing electronic examination impersonation. This study aims to address this gap by performing a model using face recognition: Labeled Face in the Wild (LFW), Custom Dataset, algorithms using TensorFlowJs and Face Application Programming Interface (API) model. The research evaluates this model on a unified facial recognition dataset, assessing their performance based on face verification and recognition. The LFW dataset a popular benchmark dataset for face verification and recognition focuses on detecting and alignment of captured images, where TensorFlowJs extract face embedding, while the Face API verifies captured image by loading the Custom Dataset (Enrolled images) comparing with that of the recent before successful authentication. The LFW-TensorFlowJs combines these approaches to leverage both Secure and accurate information. Results shows that integrating LFW, TensorFlowJs and Face API model outperforms the standalone LFW.

Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face verification and identification, involves face feature discrimination. However, the traditional softmax loss of deep CNNs usually lacks the power of discrimination. To address this problem, recently several loss functions such as center loss, large margin softmax loss, and angular softmax loss have been proposed. All these improved losses share the same idea: maximizing inter-class variance and minimizing intra-class variance. In this paper, we propose a novel loss function, namely large margin cosine loss (LMCL), to realize this idea from a different perspective. More specifically, we reformulate the softmax loss as a cosine loss by L2 normalizing both features and weight vectors to remove radial variations, based on which a cosine margin term is introduced to further maximize the decision margin in the angular space. As a result, minimum intra-class variance and maximum inter-class variance are achieved by virtue of normalization and cosine decision margin maximization. We refer to our model trained with LMCL as CosFace. Extensive experimental evaluations are conducted on the most popular public-domain face recognition datasets such as MegaFace Challenge, Youtube Faces (YTF) and Labeled Face in the Wild (LFW). We achieve the state-of-the-art performance on these benchmarks, which confirms the effectiveness of our proposed approach.

Convolutional neural networks have significantly boosted the performance of face recognition in recent years due to its high capacity in learning discriminative features. In order to enhance the discriminative power of the deeply learned features, we propose a new supervision signal named marginal loss for deep face recognition. Specifically, the marginal loss simultaneously minimises the intra-class variances as well as maximises the inter-class distances by focusing on the marginal samples. With the joint supervision of softmax loss and marginal loss, we can easily train a robust CNNs to obtain more discriminative deep features. Extensive experiments on several relevant face recognition benchmarks, Labelled Faces in the Wild (LFW), YouTube Faces (YTF), Cross-Age Celebrity Dataset (CACD), Age Database (AgeDB) and MegaFace Challenge, prove the effectiveness of the proposed marginal loss.

Application of Face Recognition Method Under Deep Learning Algorithm in Embedded Systems

Many modern computer vision algorithms are built atop of a set of low-level feature operators (such as SIFT [1], [2]; HOG [3], [4]; or LBP [5], [6]) that transform raw pixel values into a representation better suited to subsequent processing and classification. While the choice of feature representation is often not central to the logic of a given algorithm, the quality of the feature representation can have critically important implications for performance. Here, we demonstrate a large-scale feature search approach to generating new, more powerful feature representations in which a multitude of complex, nonlinear, multilayer neuromorphic feature representations are randomly generated and screened to find those best suited for the task at hand. In particular, we show that a brute-force search can generate representations that, in combination with standard machine learning blending techniques, achieve state-of-the-art performance on the Labeled Faces in the Wild (LFW) [7] unconstrained face recognition challenge set. These representations outperform previous state-of-the-art approaches, in spite of requiring less training data and using a conceptually simpler machine learning backend. We argue that such large-scale-search-derived feature sets can play a synergistic role with other computer vision approaches by providing a richer base of features with which to work.

High-throughput-derived biologically-inspired features for unconstrained face recognition

Fine-grained face verification: FGLFW database, baselines, and human-DCMN partnership

Face Recognition (FR) problem is one of the significant fields in computer vision. FR is used to identify the faces that appear over distributed cameras over the network. The problem of face recognition can be divided into two categories, the first is recognition with more than one sample per person, which can be called traditional face recognition problem. The second is the recognition of faces using only a Single Sample Per Person (SSPP). The efficiency of face recognition systems decreases because of limited references especially (SSPP) and faces taken in the Operational Domain (OD) different from faces in the Enrollment Domain (ED) in illumination, pose, low-resolution, and blurriness. This paper proposed a method that deals with all problems related to face recognition with SSPP. 3D face reconstruction is used to increase the reference gallery set with different poses and generate a design domain dictionary to overcome the problem of limited reference. Besides, the design domain dictionary is used to feed different deep learning models. Face illumination transfer techniques are utilized to overcome the illumination problem. Labeled Faces in the Wild (LFW) dataset is used to train Super-Resolution Generative Adversarial Network (SRGAN) to overcome the low-resolution problem. Deblur Generative Adversarial Network (DeblurGAN) is trained on the LFW dataset to overcome the problem of blurriness. The proposed method is evaluated using the Chokepoint dataset and COX-S2V dataset. The final results confirm an overall enhancement in accuracy compared to techniques that use SSPP for face recognition (generic learning and face synthesizing approaches). Also, the proposed method outperforms of Traditional and Deep Learning (TDL) method accuracy, which uses SSPP for face recognition.

Deep learning, in particular Convolutional Neural Network (CNN), has achieved promising results in face recognition recently. However, it remains an open question: why CNNs work well and how to design a 'good' architecture. The existing works tend to focus on reporting CNN architectures that work well for face recognition rather than investigate the reason. In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible. Specifically, we use public database LFW (Labeled Faces in the Wild) to train CNNs, unlike most existing CNNs trained on private databases. We propose three CNN architectures which are the first reported architectures trained using LFW data. This paper quantitatively compares the architectures of CNNs and evaluate the effect of different implementation choices. We identify several useful properties of CNN-FRS. For instance, the dimensionality of the learned features can be significantly reduced without adverse effect on face recognition accuracy. In addition, traditional metric learning method exploiting CNN-learned features is evaluated. Experiments show two crucial factors to good CNN-FRS performance are the fusion of multiple CNNs and metric learning. To make our work reproducible, source code and models will be made publicly available.

The complexity and applicability of facial recognition in the growing domains of security and authentication, payment, advertising and health care have accelerated the research and development of this niche in the artificial intelligence (AI) field. A facial recognition system utilizes technologies to recognize a human face through mapping of distinct facial features from raw data such as photography and video to information of known faces stored in the database. Recognizing faces in real-world images is a challenging task. Generally, a facial recognition system involves multiple processes such as facial detection, feature extraction, face matching and confidence scoring in which various techniques and algorithms are available in the form of libraries and frameworks. In this paper, an investigation is conducted using two pipelines to identify the effectiveness of two prevalent open-source libraries, OpenCV and OpenFace, on real-time face recognition system. In the OpenCV pipeline, Viola –Jones algorithm is chosen for face detection, while feature extraction is conducted using local binary pattern histogram (LBPH). Face detection is performed using dlib, while feature extraction is conducted using deep learning algorithm in the OpenFace pipeline. Performance measures of both pipelines are evaluated using Labelled Faces in the Wild (LFW) as a benchmark data set. In addition, a locally populated data set consisting of images of personnel who are given access to the office door system is used to experiment on the applicability of these pipelines on real streaming data. OpenFace achieved an AUROC of 0.98, while OpenCV scored 0.94. Both experiments inferred that facial recognition system with OpenFace pipeline outperforms OpenCV in all aspects of performance measures. Further development demonstrates the successful implementation of OpenFace pipeline to a functional prototype in replacing the manual door access control.

Face recognition has become a fascinating field for researchers. The motivation behind the enormous interest in the topic is the need to improve the accuracy of many real-time applications. The complexity of the human face and the changes due to different effects make it more challenging to design as well as implement a powerful computational system for human face recognition. In this paper, we presented an enhanced approach to improve human face recognition using a back-propagation neural network (BPNN) and features extraction based on the correlation between the training images. A key contribution of this paper is the generation of a new set called the T-Dataset from the original training data set, which is used to train the BPNN. We generated the T-Dataset using the correlation between the training images without using a common technique of image density. The correlated T-Dataset provides a high distinction layer between the training images, which helps the BPNN to converge faster and achieve better accuracy. Data and features reduction are essential in the face recognition process, and researchers have recently focused on the modern neural network. Therefore, we used a local binary pattern histogram descriptor to prove that there is potential improvement even using traditional methods. We applied five distance measurement algorithms and then combined them to obtain the T-Dataset, which we fed into the BPNN. We achieved higher face recognition accuracy with less computational cost compared with the current approach by using reduced image features. We test the proposed framework on two small data sets, the YALE and AT&T data sets, as the ground truth. We achieved tremendous accuracy. Furthermore, we evaluate our method on one of the state-of-the-art benchmark data sets, Labeled Faces in the Wild (LFW), where we produce a competitive face recognition performance.

Face recognition has become a fascinating field for researchers. The motivation behind the enormous interest in the topic is the need to improve the accuracy of many real-time applications. The complexity of the human face and the changes due to different effects make it more challenging to design as well as implement a powerful computational system for human face recognition. In this work, we presented an enhanced approach to improve human face recognition using a Back-Propagation Neural Network (BPNN) and features extraction based on the correlation between the training images. A key contribution of this work is the generation of a new set called the T-Dataset from the original training dataset, which is used to train the BPNN. We generated the T-Dataset utilizing the correlation between the training images without using a conventional technique of image density. The correlated T-Dataset provides a high distinction layer between the training images, which helps the BPNN to converge faster and achieve better accuracy. Data and features reduction is essential in the face recognition process, and researchers have recently focused on the modern Neural Network (NN). Therefore, we used a Principal Component Analysis (PCA) descriptor to prove that there is a potential improvement even using traditional methods. We applied five distance measurement algorithms and then combined them to obtain the T-Dataset, which we fed into the BPNN. We achieved higher face recognition accuracy with less computational cost compared to the current approach by using reduced image features. We test the proposed framework on two small datasets, the YALE and AT&T datasets, as the ground truth. We achieved tremendous accuracy. Furthermore, we evaluate our method on one of the state-of-the-art benchmark datasets, Labeled Faces in the Wild (LFW), where we produce a competitive face recognition performance. Also, we proposed an enhanced framework to improve the face registration using deep transfer learning. We used pre-trained models such as ResNet50 and SeNet50 which trained on the VGGFace2 dataset. We used the LFW dataset to evaluate our method, and we achieve high accuracy.

Rectilinear face recognition models suffer from severe performance degradation when applied to fisheye images captured by 360° back-to-back dual fisheye cameras. We propose a novel face rectification method to combat the effect of fisheye image distortion on face recognition. The method consists of a classification network and a restoration network specifically designed to handle the non-linear property of fisheye projection. The classification network classifies an input fisheye image according to its distortion level. The restoration network takes a distorted image as input and restores the rectilinear geometric structure of the face. The performance of the proposed method is tested on an end-to-end face recognition system constructed by integrating the proposed rectification method with a conventional rectilinear face recognition system. The face verification accuracy of the integrated system is 99.18% when tested on images in the synthetic Labeled Faces in the Wild (LFW) dataset and 95.70% for images in a real image dataset, resulting in an average accuracy improvement of 6.57% over the conventional face recognition system. For face identification, the average improvement over the conventional face recognition system is 4.51%.

At the present, the use of face masks is growing day by day and it is mandated in most places across the world. People are encouraged to cover their faces when in public areas to avoid the spread of infection which can minimize the transmission of Covid-19 by 65 percent (according to the public health officials). So, it is important to detect people not wearing face masks. Additionally, face recognition has been applied to a wide area for security verification purposes since its performance, accuracy, and reliability [15] are better than any other traditional techniques like fingerprints, passwords, PINs, and so on. In recent years, facial recognition is becoming a challenging task because of various occlusions or masks like the existence of sunglasses, scarves, hats, and the use of make-up or disguise ingredients. So, the face recognition accuracy rate is affected by these types of masks. Moreover, the use of face masks has made conventional facial recognition technology ineffective in many scenarios, such as face authentication, security check, tracking school, and unlocking phones and laptops. As a result, we proposed a solution, Masked Facial Recognition (MFR) which can identify masked and unmasked people so individuals wearing a face mask do not need to take it out to authenticate themselves. We used the Deep Learning model, Inception ResNet V1 to train our model. The CASIA dataset [17] is applied for training images and the LFW (Labeled Faces in the Wild) dataset [18] is used for model evaluation purposes. The masked datasets are created using a Computer Vision-based approach (Dlib), We received an accuracy of over 96 percent for our three different trained models. As a result, the purposed work could be utilized effortlessly for both masked and unmasked face recognition and detection systems that are designed for safety and security verification purposes without any challenges.

In face recognition, face rotation alignment is an important part of the recognition process. In this paper, we present a hierarchical detector system using eye and eye-pair detectors combined with a geometrical method for calculating the in-plane angle of a face image. Two feature extraction methods, the restricted Boltzmann machine and the histogram of oriented gradients, are compared to extract feature vectors from a sliding window. Then a support vector machine is used to accurately localize the eyes. After the eye coordinates are obtained through our eye detector, the in-plane angle is estimated by calculating the arc-tangent of horizontal and vertical parts of the distance between left and right eye center points. By using this calculated in-plane angle, the face is subsequently rotationally aligned. We tested our approach on three different face datasets: IMM, Labeled Faces in the Wild (LFW) and FERET. Moreover, to compare the effect of rotational aligning on face recognition performance, we performed experiments using a face recognition method using rotationally aligned and non-aligned face images from the IMM dataset. The results show that our method calculates the in-plane rotation angle with high precision and this leads to a significant gain in face recognition performance.